Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2505
    Prev
    Next
    INDEX
    Explanations

    technical terms related to message queuing and service-oriented architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pubsub and message queue topics

    np_acts-logits-general · gemini-2.0-flash

    pub/sub topic name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nawr
    -0.56
    EndContext
    -0.54
     hefyd
    -0.53
     Irons
    -0.53
     Meiji
    -0.51
     Putih
    -0.50
    ValueStyle
    -0.49
    Skocz
    -0.49
    RTEX
    -0.49
    heet
    -0.48
    POSITIVE LOGITS
     topic
    1.22
     Topic
    1.19
    Topic
    1.17
    topic
    1.13
     topics
    1.11
     TOPIC
    1.05
     Topics
    1.01
     consumer
    0.97
     Consumer
    0.96
    Topics
    0.95
    Activations Density 0.268%

    No Known Activations